技术领域Technical field
本发明涉及数据管理领域，特别涉及一种基于舆情热点的数据管理方法和系统。The present invention relates to the field of data management, and in particular to a data management method and system based on public opinion hot spots.
背景技术Background technique
随着计算机互联网产业的飞速发展，抖音、快手等短视频平台发展迅速，社交媒体上产生了大量的网络数据(短视频、网页等)，浏览网络数据逐渐成为了人们手机上网的主要方式。With the rapid development of the computer Internet industry, short video platforms such as Douyin and Kuaishou have developed rapidly, and a large amount of network data (short videos, web pages, etc.) has been generated on social media. Browsing network data has gradually become the main way for people to access the Internet on mobile phones.
目前，为了提高用户访问体验，出现了根据用户的偏好进行合适的信息推送技术，根据平时用户的经常浏览的信息，向用户推送相关的信息，然而这样的技术会导致用户屏蔽掉一些热点信息，而上网主要是为了紧追时代的热点，因此，亟需一种可以基于舆情热点的数据管理方法。At present, in order to improve user access experience, appropriate information push technology has emerged based on user preferences, and pushes relevant information to users based on the information that users usually browse. However, such technology will cause users to block some hot information. The main purpose of surfing the Internet is to keep up with the hot topics of the times. Therefore, a data management method that can be based on public opinion hot spots is urgently needed.
发明内容Contents of the invention
本发明的主要目的为提供一种基于舆情热点的数据管理方法和系统，旨在解决根据用户的偏好进行合适的信息推送技术会导致用户屏蔽掉一些热点信息的问题。The main purpose of the present invention is to provide a data management method and system based on public opinion hot spots, aiming to solve the problem that appropriate information push technology based on user preferences will cause users to block some hot information.
本发明提供了一种基于舆情热点的数据管理方法，包括：The present invention provides a data management method based on public opinion hot spots, including:
基于网络热点获取各个网络热点相关的多个热点评论；Obtain multiple hot comments related to each network hot spot based on network hot spots;
从各个热点评论中获取各个预设维度的舆情评论词；Obtain the public opinion comment words of each preset dimension from each hot comment;
将各个所述舆情评论词按照预设的转化关系转化为维度数值；Convert each of the public opinion comment words into dimensional values according to the preset conversion relationship;
按照各个预设维度将各所述热点评论对应的所述维度数值进行提取，得到各预设维度对应的维度数值集合；Extract the dimension values corresponding to each hot comment according to each preset dimension to obtain a set of dimension values corresponding to each preset dimension;
计算各所述维度数值集合的波动指标值；所述波动指标值用于反应所述维度数值集合中的波动情况；Calculate the fluctuation index value of each of the dimension value sets; the fluctuation index value is used to reflect the fluctuation situation in the dimension value set;
选取波动指标值大于预设指标值的预设维度作为目标维度；Select the preset dimension whose volatility indicator value is greater than the preset indicator value as the target dimension;
获取更新前的第一数据分类标准，并基于所述目标维度更新所述第一数据分类标准，得到第二数据分类标准；Obtain the first data classification standard before update, and update the first data classification standard based on the target dimension to obtain the second data classification standard;
从预设的数据库中获取多个网络数据，并针对同一目标维度采用预设的线性分类器设置两条线性函数其中，bt＝bt-1+mt，且b1＝m1，mt表示与分类标准相关的常数，bt表示第t条线性函数的偏置量，bt-1表示第t-1条线性函数的偏置量，t为正整数，w表示权重向量，且维数与维度数值集合的数量相同，ft(x)表示第t条线性函数，x表示网络数据，W为预设的参数；Obtain multiple network data from the preset database, and use the preset linear classifier to set two linear functions for the same target dimension. Among them, bt =bt-1 +mt , and b1 =m1 , mt represents the constant related to the classification standard, bt represents the offset of the t-th linear function, and bt-1 represents the t-th linear function -The offset of 1 linear function, t is a positive integer, w represents the weight vector, and the number of dimensions is the same as the number of dimension value sets, ft (x) represents the t-th linear function, x represents network data, and W is preset parameters;
计算每条线性函数与各个网络数据的欧式距离，并提取每条线性函数最大欧式距离和最小欧式距离，并将二者之差作为对应线性函数的信息距离；Calculate the Euclidean distance between each linear function and each network data, extract the maximum Euclidean distance and the minimum Euclidean distance of each linear function, and use the difference between the two as the information distance of the corresponding linear function;
根据公式计算同一目标维度的两条线性函数的信息距离的变换参数Ai；其中，tn表示第n个信息距离，T(tn)表示基于tn的预设计算函数；According to the formula Calculate the transformation parameter Ai of the information distance of two linear functions of the same target dimension; where tn represents the nth information distance, and T(tn ) represents the preset calculation function based on tn ;
判断所述变换参数Ai是否在预设的范围内；Determine whether the transformation parameter Ai is within a preset range;
若在预设的范围内，则基于两条线性函数从网络数据库中选取多个网络数据，以形成所述网络热点相关推荐数据包。If it is within the preset range, multiple network data are selected from the network database based on two linear functions to form the network hotspot related recommendation data package.
进一步地，所述计算各所述维度数值集合的波动指标值的步骤，包括：Further, the step of calculating the fluctuation index value of each dimension value set includes:
根据公式计算各个所述维度数值集合的波动指标值，其中/>其中，Ei表示第i个维度数值集合的所述波动指标值，当pij＝0时，定义limpij→0pijlnpij＝0，pij表示第i个维度数值集合中的第j个热点评论对应的中间值，/>表示第i个维度数值集合中的第j个热点评论对应的标准值，n表示热点评论的个数，xij表示第i个维度数值集合中的第j个热点评论对应的维度数值，min(xij)和max(xij)分别表示第i个维度数值集合中最小值和最大值。According to the formula Calculate the volatility index value of each dimension value set, where/> Among them, Ei represents the fluctuation index value of the i-th dimension value set. When pij =0, define limpij→0 pij lnpij =0, and pij represents the j-th value set of the i-th dimension. The median value corresponding to hot comments,/> represents the standard value corresponding to the j-th hot comment in the i-th dimension value set, n represents the number of hot comments, xij represents the dimension value corresponding to the j-th hot comment in the i-th dimension value set, min( xij ) and max(xij ) respectively represent the minimum value and maximum value in the i-th dimension value set.
进一步地，所述计算每条线性函数与各个网络数据的欧式距离的步骤，包括：Further, the step of calculating the Euclidean distance between each linear function and each network data includes:
将所述波动指标值和多个所述网络热点输入至预设的函数获取模型中，得到对应的转换函数；其中，所述函数获取模型根据不同的网络热点和指标值作为输入，以及根据对应的转换函数作为输出训练而成；Input the fluctuation index value and multiple network hot spots into a preset function acquisition model to obtain the corresponding conversion function; wherein, the function acquisition model takes different network hot spots and index values as input, and according to the corresponding The transformation function is trained as the output;
根据所述转换函数对所述网络数据进行空间映射，得到每个网络数据映射后的目标网络数据；Perform spatial mapping on the network data according to the conversion function to obtain the target network data mapped by each network data;
基于所述目标网络数据计算计算每条线性函数与对应网络数据的欧式距离。The Euclidean distance between each linear function and the corresponding network data is calculated based on the target network data.
进一步地，所述判断所述变换参数Ai是否在预设的范围内的步骤之后，还包括：Further, after the step of determining whether the transformation parameter Ai is within a preset range, the step further includes:
若不在预设的范围内，则调整所述线性函数中的权重向量，直至所述变换参数在所述预设的范围内，得到两个目标线性函数；If it is not within the preset range, adjust the weight vector in the linear function until the transformation parameter is within the preset range, and obtain two target linear functions;
基于两个所述目标线性函数从网络数据库中选取多个网络数据，以形成所述网络热点相关推荐数据包。A plurality of network data are selected from a network database based on the two target linear functions to form the network hotspot related recommendation data package.
进一步地，所述若在预设的范围内，则基于两条线性函数从网络数据库中选取多个网络数据，以形成所述网络热点相关推荐数据包的步骤之后，还包括：Further, after the step of selecting multiple network data from the network database based on two linear functions to form the network hotspot related recommendation data package if it is within a preset range, it also includes:
获取各个选取的网络数据的时间信息；Obtain the time information of each selected network data;
基于所述时间信息为各个网络数据设置优先级顺序；Set a priority order for each network data based on the time information;
基于所述优先级顺序向用户有序推送各个所述网络数据。Push each of the network data to the user in an orderly manner based on the priority order.
本发明还提供了一种基于舆情热点的数据管理系统，包括：The present invention also provides a data management system based on public opinion hot spots, including:
第一获取模块，用于基于网络热点获取各个网络热点相关的多个热点评论；The first acquisition module is used to acquire multiple hotspot comments related to each network hotspot based on network hotspots;
第二获取模块，用于从各个热点评论中获取各个预设维度的舆情评论词；The second acquisition module is used to obtain public opinion comment words of each preset dimension from each hot comment;
转化模块，用于将各个所述舆情评论词按照预设的转化关系转化为维度数值；The conversion module is used to convert each of the public opinion comment words into dimensional values according to the preset conversion relationship;
提取模块，用于按照各个预设维度将各所述热点评论对应的所述维度数值进行提取，得到各维度对应的维度数值集合；An extraction module, configured to extract the dimension values corresponding to each of the hot comments according to each preset dimension to obtain a set of dimension values corresponding to each dimension;
第一计算模块，用于计算各所述维度数值集合的波动指标值；所述波动指标值用于反应所述维度数值集合中的波动情况；The first calculation module is used to calculate the fluctuation index value of each of the dimension value sets; the fluctuation index value is used to reflect the fluctuation situation in the dimension value set;
第一选取模块，用于选取波动指标值大于预设指标值的预设维度作为目标维度；The first selection module is used to select a preset dimension with a fluctuation index value greater than the preset index value as the target dimension;
第三获取模块，用于获取更新前的第一数据分类标准，并基于所述目标维度更新所述第一数据分类标准，得到第二数据分类标准；The third acquisition module is used to obtain the first data classification standard before updating, and update the first data classification standard based on the target dimension to obtain the second data classification standard;
第四获取模块，用于从预设的数据库中获取多个网络数据，并针对同一目标维度采用预设的线性分类器设置两条线性函数其中，bt＝bt-1+mt，且b1＝m1，mt表示与分类标准相关的常数，bt表示第t条线性函数的偏置量，bt-1表示第t-1条线性函数的偏置量，t为正整数，w表示权重向量，且维数与维度数值集合的数量相同，ft(x)表示第t条线性函数，x表示网络数据，W为预设的参数；The fourth acquisition module is used to acquire multiple network data from a preset database, and use a preset linear classifier to set two linear functions for the same target dimension. Among them, bt =bt-1 +mt , and b1 =m1 , mt represents the constant related to the classification standard, bt represents the offset of the t-th linear function, and bt-1 represents the t-th linear function -The offset of 1 linear function, t is a positive integer, w represents the weight vector, and the number of dimensions is the same as the number of dimension value sets, ft (x) represents the t-th linear function, x represents network data, and W is preset parameters;
第二计算模块，用于计算每条线性函数与各个网络数据的欧式距离，并提取每条线性函数最大欧式距离和最小欧式距离，并将二者之差作为对应线性函数的信息距离；The second calculation module is used to calculate the Euclidean distance between each linear function and each network data, and extract the maximum Euclidean distance and minimum Euclidean distance of each linear function, and use the difference between the two as the information distance of the corresponding linear function;
第三计算模块，用于根据公式计算同一目标维度的两条线性函数的信息距离的变换参数Ai；其中，tn表示第n个信息距离，T(tn)表示基于tn的预设计算函数；The third calculation module is used according to the formula Calculate the transformation parameter Ai of the information distance of two linear functions of the same target dimension; where tn represents the nth information distance, and T(tn ) represents the preset calculation function based on tn ;
判断模块，用于判断所述变换参数Ai是否在预设的范围内；A judgment module, used to judge whether the transformation parameter Ai is within a preset range;
第二选取模块，用于若在预设的范围内，则基于两条线性函数从网络数据库中选取多个网络数据，以形成所述网络热点相关推荐数据包。The second selection module is used to select multiple network data from the network database based on two linear functions to form the network hotspot related recommendation data package if the data is within a preset range.
进一步地，所述第二计算模块，包括：Further, the second computing module includes:
输入子模块，用于将所述波动指标值和多个所述网络热点输入至预设的函数获取模型中，得到对应的转换函数；其中，所述函数获取模型根据不同的网络热点和指标值作为输入，以及根据对应的转换函数作为输出训练而成；The input submodule is used to input the fluctuation index value and a plurality of the network hot spots into a preset function acquisition model to obtain the corresponding conversion function; wherein the function acquisition model is based on different network hot spots and index values. As input, and trained according to the corresponding transformation function as output;
映射子模块，用于根据所述转换函数对所述网络数据进行空间映射，得到每个网络数据映射后的目标网络数据；A mapping submodule, used to spatially map the network data according to the conversion function to obtain the target network data mapped by each network data;
计算子模块，用于基于所述目标网络数据计算计算每条线性函数与对应网络数据的欧式距离。The calculation submodule is used to calculate the Euclidean distance between each linear function and the corresponding network data based on the target network data.
进一步地，所述第一计算模块，包括：Further, the first computing module includes:
波动指标值计算子模块，用于根据公式计算各个所述维度数值集合的波动指标值，其中/>其中，Ei表示第i个维度数值集合的所述波动指标值，当pij＝0时，定义limpij→0pijlnpij＝0，pij表示第i个维度数值集合中的第j个热点评论对应的中间值，/>表示第i个维度数值集合中的第j个热点评论对应的标准值，n表示热点评论的个数，xij表示第i个维度数值集合中的第j个热点评论对应的维度数值，min(xij)和max(xij)分别表示第i个维度数值集合中最小值和最大值。Volatility indicator value calculation submodule, used to calculate according to the formula Calculate the volatility index value of each dimension value set, where/> Among them, Ei represents the fluctuation index value of the i-th dimension value set. When pij =0, define limpij→0 pij lnpij =0, and pij represents the j-th value set of the i-th dimension. The median value corresponding to hot comments,/> represents the standard value corresponding to the j-th hot comment in the i-th dimension value set, n represents the number of hot comments, xij represents the dimension value corresponding to the j-th hot comment in the i-th dimension value set, min( xij ) and max(xij ) respectively represent the minimum value and maximum value in the i-th dimension value set.
进一步地，所述基于舆情热点的数据管理系统，还包括：Further, the data management system based on public opinion hot spots also includes:
调整模块，用于若不在预设的范围内，则调整所述线性函数中的权重向量，直至所述变换参数在所述预设的范围内，得到两个目标线性函数；an adjustment module, configured to adjust the weight vector in the linear function until the transformation parameter is within the preset range if it is not within the preset range, and obtain two target linear functions;
网络数据选取模块，用于基于两个所述目标线性函数从网络数据库中选取多个网络数据，以形成所述网络热点相关推荐数据包。A network data selection module is used to select multiple network data from the network database based on the two target linear functions to form the network hotspot related recommendation data package.
进一步地，所述基于舆情热点的数据管理系统，还包括：Further, the data management system based on public opinion hot spots also includes:
时间信息获取模块，用于获取各个选取的网络数据的时间信息；The time information acquisition module is used to obtain the time information of each selected network data;
优先级顺序设置模块，用于基于所述时间信息为各个网络数据设置优先级顺序；A priority order setting module, configured to set a priority order for each network data based on the time information;
推送模块，用于基于所述优先级顺序向用户有序推送各个所述网络数据。A push module, configured to push each of the network data to users in an orderly manner based on the priority order.
本发明的有益效果：通过获取网络热点的热点评论，并以此更新数据分类标准，从而获取到与网络热点相关的推荐数据包，实现了从网络热点的角度来为用户推荐网络数据，从而可以使用户可以紧随时代的热点，满足了用户的需求。Beneficial effects of the present invention: by obtaining hotspot comments of network hotspots and updating data classification standards thereby obtaining recommendation data packets related to network hotspots, it is possible to recommend network data to users from the perspective of network hotspots, thereby enabling It enables users to keep up with the hot topics of the times and meets the needs of users.
附图说明Description of the drawings
图1是本发明一实施例的一种基于舆情热点的数据管理方法的流程示意图；Figure 1 is a schematic flow chart of a data management method based on public opinion hot spots according to an embodiment of the present invention;
图2是本发明一实施例的一种基于舆情热点的数据管理系统的结构示意框图。Figure 2 is a schematic structural block diagram of a data management system based on public opinion hot spots according to an embodiment of the present invention.
本发明目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。The realization of the purpose, functional features and advantages of the present invention will be further described with reference to the embodiments and the accompanying drawings.
具体实施方式Detailed ways
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明的一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present invention.
需要说明，本发明实施例中所有方向性指示(诸如上、下、左、右、前、后等)仅用于解释在某一特定姿态(如附图所示)下各部件之间的相对位置关系、运动情况等，如果该特定姿态发生改变时，则该方向性指示也相应地随之改变，所述的连接可以是直接连接，也可以是间接连接。It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiment of the present invention are only used to explain the relative relationship between components in a specific posture (as shown in the drawings). Positional relationships, movement conditions, etc., if the specific posture changes, the directional indication will also change accordingly. The connection may be a direct connection or an indirect connection.
本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。The term "and/or" in this article is just an association relationship that describes related objects, indicating that there can be three relationships. For example, A and B can mean: A exists alone, A and B exist simultaneously, and B exists alone. three conditions.
另外，在本发明中如涉及“第一”、“第二”等的描述仅用于描述目的，而不能理解为指示或暗示其相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。另外，各个实施例之间的技术方案可以相互结合，但是必须是以本领域普通技术人员能够实现为基础，当技术方案的结合出现相互矛盾或无法实现时应当认为这种技术方案的结合不存在，也不在本发明要求的保护范围之内。In addition, descriptions such as "first", "second", etc. in the present invention are for descriptive purposes only and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of indicated technical features. Therefore, features defined as "first" and "second" may explicitly or implicitly include at least one of these features. In addition, the technical solutions in various embodiments can be combined with each other, but it must be based on the realization by those of ordinary skill in the art. When the combination of technical solutions is contradictory or cannot be realized, it should be considered that such a combination of technical solutions does not exist. , nor within the protection scope required by the present invention.
参照图1，本发明提出一种基于舆情热点的数据管理方法，包括：Referring to Figure 1, the present invention proposes a data management method based on public opinion hot spots, including:
S1：基于网络热点获取各个网络热点相关的多个热点评论；S1: Obtain multiple hotspot comments related to each network hotspot based on network hotspots;
S2：从各个热点评论中获取各个预设维度的舆情评论词；S2: Obtain the public opinion comment words of each preset dimension from each hot comment;
S3：将各个所述舆情评论词按照预设的转化关系转化为维度数值；S3: Convert each of the public opinion comment words into dimensional values according to the preset conversion relationship;
S4：按照各个预设维度将各所述热点评论对应的所述维度数值进行提取，得到各维度对应的维度数值集合；S4: Extract the dimension values corresponding to each hot comment according to each preset dimension to obtain a set of dimension values corresponding to each dimension;
S5：计算各所述维度数值集合的波动指标值；所述波动指标值用于反应所述维度数值集合中的波动情况；S5: Calculate the fluctuation index value of each dimension value set; the fluctuation index value is used to reflect the fluctuation situation in the dimension value set;
S6：选取波动指标值大于预设指标值的预设维度作为目标维度；S6: Select the preset dimension whose volatility indicator value is greater than the preset indicator value as the target dimension;
S7：获取更新前的第一数据分类标准，并基于所述目标维度更新所述第一数据分类标准，得到第二数据分类标准；S7: Obtain the first data classification standard before update, update the first data classification standard based on the target dimension, and obtain the second data classification standard;
S8：从预设的数据库中获取多个网络数据，并针对同一目标维度采用预设的线性分类器设置两条线性函数其中，bt＝bt-1+mt，且b1＝m1，mt表示与分类标准相关的常数，bt表示第t条线性函数的偏置量，bt-1表示第t-1条线性函数的偏置量，t为正整数，w表示权重向量，且维数与维度数值集合的数量相同，ft(x)表示第t条线性函数，x表示网络数据，W为预设的参数；S8: Obtain multiple network data from the preset database, and use the preset linear classifier to set two linear functions for the same target dimension. Among them, bt =bt-1 +mt , and b1 =m1 , mt represents the constant related to the classification standard, bt represents the offset of the t-th linear function, and bt-1 represents the t-th linear function -The offset of 1 linear function, t is a positive integer, w represents the weight vector, and the number of dimensions is the same as the number of dimension value sets, ft (x) represents the t-th linear function, x represents network data, and W is preset parameters;
S9：计算每条线性函数与各个网络数据的欧式距离，并提取每条线性函数最大欧式距离和最小欧式距离，并将二者之差作为对应线性函数的信息距离；S9: Calculate the Euclidean distance between each linear function and each network data, extract the maximum Euclidean distance and the minimum Euclidean distance of each linear function, and use the difference between the two as the information distance of the corresponding linear function;
S10：根据公式计算同一目标维度的两条线性函数的信息距离的变换参数Ai；其中，tn表示第n个信息距离，T(tn)表示基于tn的预设计算函数；S10: According to the formula Calculate the transformation parameter Ai of the information distance of two linear functions of the same target dimension; where tn represents the nth information distance, and T(tn ) represents the preset calculation function based on tn ;
S11：判断所述变换参数Ai是否在预设的范围内；S11: Determine whether the transformation parameter Ai is within a preset range;
S12：若在预设的范围内，则基于两条线性函数从网络数据库中选取多个网络数据，以形成所述网络热点相关推荐数据包。S12: If within the preset range, select multiple network data from the network database based on two linear functions to form the network hotspot related recommendation data package.
如上述步骤S1所述，基于网络热点获取各个网络热点相关的多个热点评论，其中，网络热点为热点新闻相关的词条，例如世界杯，梅西等相关热点新闻、短视频等，具体的热点可以从各个APP的头条进行获取，例如微博的头条等，在获取到对应的网络热点后，其对应的热点评论中含有大多数用户关注的东西，因此，获取到对应的热点评论以作为推送数据的依据，获取的方式可以直接从评论区获取高赞的一些评论。As described in step S1 above, multiple hot comments related to each network hot spot are obtained based on network hot spots. Among them, network hot spots are entries related to hot news, such as the World Cup, Messi and other related hot news, short videos, etc. Specific hot spots It can be obtained from the headlines of each APP, such as the headlines of Weibo, etc. After obtaining the corresponding network hot spots, the corresponding hot comments contain things that most users are concerned about. Therefore, the corresponding hot comments are obtained as push notifications. The basis of the data can be obtained directly from the comment area by obtaining some highly praised comments.
如上述步骤S2所述，从各个热点评论中获取各个预设维度的舆情评论词，需要说明的是，该预设维度均是预先确定的维度，例如足球，篮球等，其对应的舆情评论词可以是正面的词也可以是负面的词，可以根据词性的极性来进行计算。As described in step S2 above, the public opinion comment words of each preset dimension are obtained from each hot comment. It should be noted that the preset dimensions are all predetermined dimensions, such as football, basketball, etc., and their corresponding public opinion comment words It can be a positive or negative word and can be calculated based on the polarity of the part of speech.
如上述步骤S3所述，将各个所述舆情评论词按照预设的转化关系转化为维度数值，具体地，可以事先设定舆情评论词与维度数值的对应关系，后续可以根据舆情评论词获取到对应的维度数值。As described in step S3 above, each public opinion comment word is converted into a dimension value according to a preset conversion relationship. Specifically, the corresponding relationship between the public opinion comment word and the dimension value can be set in advance, and subsequently the public opinion comment word can be obtained based on the The corresponding dimension value.
如上述步骤S4-S6所述，按照各个预设维度将各所述热点评论对应的所述维度数值进行提取，得到各维度对应的维度数值集合，计算各所述维度数值集合的波动指标值；所述波动指标值用于反应所述维度数值集合中的波动情况。当一件热点事情被多次评论，且具有多种不同的态度时，即波动指标值较大时，则认为其具有争议的点，那么对于这样的热点，用户是非常感兴趣的，因此，选取波动指标值大于预设指标值的预设维度作为目标维度，以便于筛选出对应的网络数据(即短视频或者网页等)。其中，该波动指标值可以是计算维度数值集合中的方差或平均差，还可以是通过其他计算方式，后续会详细说明，此处不再赘述。As described in steps S4-S6 above, extract the dimension values corresponding to each hot comment according to each preset dimension to obtain a set of dimension values corresponding to each dimension, and calculate the fluctuation index value of each set of dimension values; The fluctuation index value is used to reflect the fluctuation situation in the dimension value set. When a hot topic is commented on many times and has many different attitudes, that is, when the fluctuation index value is large, it is considered to be controversial. Then users are very interested in such hot topics. Therefore, Select the preset dimension with a fluctuation index value greater than the preset index value as the target dimension to filter out the corresponding network data (i.e. short videos or web pages, etc.). The fluctuation index value can be calculated by calculating the variance or average difference in the dimension value set, or by other calculation methods, which will be explained in detail later and will not be described again here.
如上述步骤S7所述，其中，第一数据分类标准是之前根据用户的浏览情况所设定的标准，也可以是基于之前的热点所设定的标准，需要说明的是，热点一般会存在并且持续一段时间，当热点更新后，则会触发对应的更新，至于第一数据分类标准则是上一次的分类标准，第一次的分类标准可以是人为的进行设定，此后每次根据实时热点触发下一分类标准的更新，具体为获取到目标维度后，将目标维度对应的维度数值集合中的元素进行求和平均，从而得到均值，将该均值覆盖第一数据分类标准中对应的维度值，从而得到第二数据分类标准，当然需要说明的是，目标维度可能具有多个，因此，对应修改的分类标准也具有多个。As described in step S7 above, the first data classification standard is a standard previously set based on the user's browsing situation, or may be a standard set based on previous hotspots. It should be noted that hotspots generally exist and After a period of time, when the hotspot is updated, the corresponding update will be triggered. As for the first data classification standard, it is the last classification standard. The first classification standard can be set manually. After that, each time it is based on the real-time hotspot Trigger the update of the next classification standard. Specifically, after obtaining the target dimension, the elements in the dimension value set corresponding to the target dimension are summed and averaged to obtain the average value, and the average value is overwritten with the corresponding dimension value in the first data classification standard. , thereby obtaining the second data classification standard. Of course, it should be noted that there may be multiple target dimensions, and therefore, there may also be multiple corresponding modified classification standards.
如上述步骤S8所述，从预设的数据库中获取多个网络数据，并针对同一目标维度采用预设的线性分类器设置两条线性函数，预设的数据库为对应的APP数据库，举例而言，可以是短视频数据库，即网络数据为短视频，其中常见的线性分类器有：贝叶斯分类、线性回归、LR、SVM(线性核)、单层感知机等。即若为N维空间，则得到的归一化线性函数为一个超平面。线性分类器就是用一个“超平面”将正、负样本隔离开，如：二维平面上的正、负样本用一条直线来进行分类；三维立体空间内的正、负样本用一个平面来进行分类；N维空间内的正负样本用一个超平面来进行分类。设置两条线性函数是为了限定范围，从而便于从数据库中筛选出想要的网络数据。As described in step S8 above, multiple network data are obtained from the preset database, and two linear functions are set using the preset linear classifier for the same target dimension. The preset database is the corresponding APP database. For example , which can be a short video database, that is, the network data is short video. Common linear classifiers include: Bayesian classification, linear regression, LR, SVM (linear kernel), single-layer perceptron, etc. That is, if it is an N-dimensional space, the obtained normalized linear function is a hyperplane. A linear classifier uses a "hyperplane" to separate positive and negative samples. For example, positive and negative samples on a two-dimensional plane are classified using a straight line; positive and negative samples in a three-dimensional space are classified on a plane. Classification; positive and negative samples in N-dimensional space are classified using a hyperplane. The two linear functions are set up to limit the range, making it easier to filter out the desired network data from the database.
如上述步骤S9所述，计算每条线性函数与各个网络数据的欧式距离，并提取每条线性函数最大欧式距离和最小欧式距离，并将二者之差作为对应线性函数的信息距离，计算每条归一化线性函数与各个目标订单的欧式距离，并提取每条归一化线性函数最大欧式距离和最小欧式距离，并将最大欧式距离减去最小欧式距离作为对应归一化线性函数的信息距离。计算欧式距离为求各个目标订单值该归一化线性函数即超平面的距离。As described in step S9 above, calculate the Euclidean distance between each linear function and each network data, extract the maximum Euclidean distance and the minimum Euclidean distance of each linear function, and use the difference between the two as the information distance of the corresponding linear function, calculate each Euclidean distance between each normalized linear function and each target order, and extract the maximum Euclidean distance and minimum Euclidean distance of each normalized linear function, and subtract the minimum Euclidean distance from the maximum Euclidean distance as the information of the corresponding normalized linear function distance. Calculating the Euclidean distance is to find the distance of the normalized linear function, that is, the hyperplane, of each target order value.
如上述步骤S10-S12所述，根据公式计算同一目标维度的两条线性函数的信息距离的变换参数Ai；判断所述变换参数Ai是否在预设的范围内；若在预设的范围内，则基于两条线性函数从网络数据库中选取多个网络数据，以形成所述网络热点相关推荐数据包。其中，tn表示第n个信息距离，T(tn)表示基于tn的预设计算函数，具体地，T(tn)＝atn+b，a和b均为常数，需要说明的是，对于两两线性函数其对应的变换参数越接近1说明其分类效果越好，反之效果越差，分类结果越好，则筛选的精度更高，从而可以获取到基于舆情热点的网络数据，以便于分享给用户，从而实现了从网络热点的角度来为用户推荐网络数据，从而可以使用户可以紧随时代的热点，满足了用户的需求。As described in steps S10-S12 above, according to the formula Calculate the transformation parameter Ai of the information distance of two linear functions of the same target dimension; determine whether the transformation parameter Ai is within the preset range; if it is within the preset range, extract the information from the network database based on the two linear functions A plurality of network data are selected to form the network hotspot related recommendation data package. Among them, tn represents the nth information distance, and T (tn ) represents the preset calculation function based on tn . Specifically, T (tn ) = atn + b, both a and b are constants. It needs to be explained. Yes, for a pairwise linear function, the closer the corresponding transformation parameter is to 1, the better the classification effect. On the contrary, the worse the effect, the better the classification result, and the higher the filtering accuracy, so that network data based on public opinion hot spots can be obtained. In order to facilitate sharing to users, it is possible to recommend network data to users from the perspective of network hot spots, so that users can follow the hot spots of the times and meet the needs of users.
在一个实施例中，所述计算每条线性函数与各个网络数据的欧式距离的步骤S9，包括：In one embodiment, the step S9 of calculating the Euclidean distance between each linear function and each network data includes:
S901：将所述波动指标值和多个所述网络热点输入至预设的函数获取模型中，得到对应的转换函数；其中，所述函数获取模型根据不同的网络热点和指标值作为输入，以及根据对应的转换函数作为输出训练而成；S901: Input the fluctuation index value and multiple network hot spots into a preset function acquisition model to obtain a corresponding conversion function; wherein the function acquisition model takes different network hot spots and index values as input, and It is trained according to the corresponding conversion function as the output;
S902：根据所述转换函数对所述网络数据进行空间映射，得到每个网络数据映射后的目标网络数据；S902: Perform spatial mapping on the network data according to the conversion function to obtain the target network data mapped by each network data;
S903：基于所述目标网络数据计算计算每条线性函数与对应网络数据的欧式距离。S903: Calculate the Euclidean distance between each linear function and the corresponding network data based on the target network data.
如上述步骤S901-S903所述，实现了对数据的处理，由于在实际的计算过程中，可能得到的函数不是线性的，但是可以将其映射至特征空间，在特征空间中可以得到对应的线性函数，因此，可以获取到适当的转换函数，具体地，可以直接进行线性分类，则该映射可以是直接进行映射，即转换函数的变化量为1。常见的转换函数具有线性转换函数、多项式转换函数、Gauss径向基转换函数等。As described in the above steps S901-S903, the data processing is realized. Since in the actual calculation process, the function obtained may not be linear, but it can be mapped to the feature space, and the corresponding linear function can be obtained in the feature space. function, therefore, an appropriate conversion function can be obtained. Specifically, linear classification can be performed directly, then the mapping can be direct mapping, that is, the variation of the conversion function is 1. Common conversion functions include linear conversion functions, polynomial conversion functions, Gauss radial basis conversion functions, etc.
在一个实施例中，所述计算各所述维度数值集合的波动指标值的步骤S5，包括：In one embodiment, the step S5 of calculating the fluctuation index value of each dimension value set includes:
S501：根据公式计算各个所述维度数值集合的波动指标值，其中/>其中，Ei表示第i个维度数值集合的所述波动指标值，当pij＝0时，定义limpij→0pijlnpij＝0，pij表示第i个维度数值集合中的第j个热点评论对应的中间值，/>表示第i个维度数值集合中的第j个热点评论对应的标准值，n表示热点评论的个数，xij表示第i个维度数值集合中的第j个热点评论对应的维度数值，min(xij)和max(xij)分别表示第i个维度数值集合中最小值和最大值。S501: According to the formula Calculate the volatility index value of each dimension value set, where/> Among them, Ei represents the fluctuation index value of the i-th dimension value set. When pij =0, define limpij→0 pij lnpij =0, and pij represents the j-th value set of the i-th dimension. The median value corresponding to hot comments,/> represents the standard value corresponding to the j-th hot comment in the i-th dimension value set, n represents the number of hot comments, xij represents the dimension value corresponding to the j-th hot comment in the i-th dimension value set, min( xij ) and max(xij ) respectively represent the minimum value and maximum value in the i-th dimension value set.
如上述步骤S501所述，实现了对波动指标值的计算，即先获取维度数值集合中的最大值与最小值，根据最大值和最小值来反应整个维度数值集合的数据波动情况，即先根据公式计算各个维度数值对应的标准值，即先将各个维度数值进行标准处理，将其进行归一化处理，避免造成的数据过大而导致计算结果出现偏差。然后根据各个维度数值对应的标准差所出现的概率pij，计算第j个所述维度数值集合的所述波动指标值。根据上述计算公式计算得到的波动指标值，其充分考虑了同一维度中各个维度数值的波动情况，并且也充分考虑了极个别值对整体波动指标值所带来的影响，使计算的波动指标值更具有参考性。As described in the above step S501, the calculation of the fluctuation index value is realized, that is, the maximum value and the minimum value in the dimension value set are first obtained, and the data fluctuation of the entire dimension value set is reflected based on the maximum value and the minimum value, that is, the data fluctuation situation of the entire dimension value set is first obtained according to formula Calculate the standard values corresponding to the values of each dimension, that is, first perform standard processing on the values of each dimension and normalize them to avoid deviations in the calculation results caused by excessive data. Then, according to the probability pij of the standard deviation corresponding to each dimension value, the fluctuation index value of the jth dimension value set is calculated. The fluctuation index value calculated according to the above calculation formula fully takes into account the fluctuation of the values of each dimension in the same dimension, and also fully considers the impact of very individual values on the overall fluctuation index value, so that the calculated fluctuation index value More reference.
在一个实施例中，所述判断所述变换参数Ai是否在预设的范围内的步骤S11之后，还包括：In one embodiment, after step S11 of determining whether the transformation parameter Ai is within a preset range, the method further includes:
S1201：若不在预设的范围内，则调整所述线性函数中的权重向量，直至所述变换参数在所述预设的范围内，得到两个目标线性函数；S1201: If it is not within the preset range, adjust the weight vector in the linear function until the transformation parameter is within the preset range, and obtain two target linear functions;
S1202：基于两个所述目标线性函数从网络数据库中选取多个网络数据，以形成所述网络热点相关推荐数据包。S1202: Select multiple network data from the network database based on the two target linear functions to form the network hotspot related recommendation data package.
如上述步骤S1201-S1202所述，当不在预设的范围内时，可以认为线性函数设置不合理，因此，需要调整其中的权重向量，调整的方式应当遵循对应的标准调整，直至变换参数在预设的范围内，得到两个目标线性函数，再基于两个所述目标线性函数从网络数据库中选取多个网络数据，以形成所述网络热点相关推荐数据包。其中选取的方式与上述选取的方式相同，此处不再赘述。As described in the above steps S1201-S1202, when it is not within the preset range, it can be considered that the linear function setting is unreasonable. Therefore, the weight vector needs to be adjusted. The adjustment method should follow the corresponding standard adjustment until the transformation parameters are within the preset range. Within the range of the assumption, two target linear functions are obtained, and then multiple network data are selected from the network database based on the two target linear functions to form the network hotspot related recommendation data package. The selection method is the same as the above selection method and will not be described again here.
在一个实施例中，所述若在预设的范围内，则基于两条线性函数从网络数据库中选取多个网络数据，以形成所述网络热点相关推荐数据包的步骤S12之后，还包括：In one embodiment, after step S12 of selecting multiple network data from the network database based on two linear functions to form the network hotspot related recommendation data package if it is within a preset range, the step S12 also includes:
S1301：获取各个选取的网络数据的时间信息；S1301: Obtain the time information of each selected network data;
S1302：基于所述时间信息为各个网络数据设置优先级顺序；S1302: Set a priority order for each network data based on the time information;
S1303：基于所述优先级顺序向用户有序推送各个所述网络数据。S1303: Push each of the network data to the user in an orderly manner based on the priority order.
如上述步骤S1301-S1303所述，实现了对网络数据的推送的先后顺序选择，使用户的体验性更好，具体地，获取选取的网络数据的时间信息，即该时间信息可以是上传的时间时间信息，若是短视频，还可以是拍摄或者制作短视频时的时间信息，本申请对此不作限定，此外，在获取大对应的时间信息后，可以为网络数据设置优先级顺序，例如可以设置为距离当前时间最近的网络数据先发送给用户，从而可以使用户可以浏览到最新的信息，从而可以紧随热点。As described in the above steps S1301-S1303, the sequence selection of pushing network data is realized to make the user experience better. Specifically, the time information of the selected network data is obtained, that is, the time information can be the upload time. The time information, if it is a short video, can also be the time information when shooting or making the short video. This application is not limited to this. In addition, after obtaining the corresponding time information, the priority order can be set for the network data. For example, it can be set The network data closest to the current time is sent to the user first, so that the user can browse the latest information and follow the hot spots.
本发明的有益效果：通过获取网络热点的热点评论，并以此更新数据分类标准，从而获取到与网络热点相关的推荐数据包，实现了从网络热点的角度来为用户推荐网络数据，从而可以使用户可以紧随时代的热点，满足了用户的需求。Beneficial effects of the present invention: by obtaining hotspot comments of network hotspots and updating data classification standards thereby obtaining recommendation data packets related to network hotspots, it is possible to recommend network data to users from the perspective of network hotspots, thereby enabling It enables users to keep up with the hot topics of the times and meets the needs of users.
参照图2，本发明还提供了一种基于舆情热点的数据管理系统，包括：Referring to Figure 2, the present invention also provides a data management system based on public opinion hot spots, including:
第一获取模块10，用于基于网络热点获取各个网络热点相关的多个热点评论；The first acquisition module 10 is used to acquire multiple hotspot comments related to each network hotspot based on network hotspots;
第二获取模块20，用于从各个热点评论中获取各个预设维度的舆情评论词；The second acquisition module 20 is used to acquire the public opinion comment words of each preset dimension from each hot comment;
转化模块30，用于将各个所述舆情评论词按照预设的转化关系转化为维度数值；The conversion module 30 is used to convert each of the public opinion comment words into dimensional values according to the preset conversion relationship;
提取模块40，用于按照各个预设维度将各所述热点评论对应的所述维度数值进行提取，得到各维度对应的维度数值集合；The extraction module 40 is used to extract the dimension values corresponding to each hot comment according to each preset dimension to obtain a set of dimension values corresponding to each dimension;
第一计算模块50，用于计算各所述维度数值集合的波动指标值；所述波动指标值用于反应所述维度数值集合中的波动情况；The first calculation module 50 is used to calculate the fluctuation index value of each of the dimension value sets; the fluctuation index value is used to reflect the fluctuation situation in the dimension value set;
第一选取模块60，用于选取波动指标值大于预设指标值的预设维度作为目标维度；The first selection module 60 is used to select a preset dimension with a fluctuation index value greater than the preset index value as the target dimension;
第三获取模块70，用于获取更新前的第一数据分类标准，并基于所述目标维度更新所述第一数据分类标准，得到第二数据分类标准；The third acquisition module 70 is used to obtain the first data classification standard before updating, and update the first data classification standard based on the target dimension to obtain the second data classification standard;
第四获取模块80，用于从预设的数据库中获取多个网络数据，并针对同一目标维度采用预设的线性分类器设置两条线性函数其中，bt＝bt-1+mt，且b1＝m1，mt表示与分类标准相关的常数，bt表示第t条线性函数的偏置量，bt-1表示第t-1条线性函数的偏置量，t为正整数，w表示权重向量，且维数与维度数值集合的数量相同，ft(x)表示第t条线性函数，x表示网络数据，W为预设的参数；The fourth acquisition module 80 is used to acquire multiple network data from a preset database, and use a preset linear classifier to set two linear functions for the same target dimension. Among them, bt =bt-1 +mt , and b1 =m1 , mt represents the constant related to the classification standard, bt represents the offset of the t-th linear function, and bt-1 represents the t-th linear function -The offset of 1 linear function, t is a positive integer, w represents the weight vector, and the number of dimensions is the same as the number of dimension value sets, ft (x) represents the t-th linear function, x represents network data, and W is preset parameters;
第二计算模块90，用于计算每条线性函数与各个网络数据的欧式距离，并提取每条线性函数最大欧式距离和最小欧式距离，并将二者之差作为对应线性函数的信息距离；The second calculation module 90 is used to calculate the Euclidean distance between each linear function and each network data, and extract the maximum Euclidean distance and the minimum Euclidean distance of each linear function, and use the difference between the two as the information distance of the corresponding linear function;
第三计算模块100，用于根据公式计算同一目标维度的两条线性函数的信息距离的变换参数Ai；其中，tn表示第n个信息距离，T(tn)表示基于tn的预设计算函数；The third calculation module 100 is used to calculate according to the formula Calculate the transformation parameter Ai of the information distance of two linear functions of the same target dimension; where tn represents the nth information distance, and T(tn ) represents the preset calculation function based on tn ;
判断模块110，用于判断所述变换参数Ai是否在预设的范围内；The judgment module 110 is used to judge whether the transformation parameter Ai is within a preset range;
第二选取模块120，用于若在预设的范围内，则基于两条线性函数从网络数据库中选取多个网络数据，以形成所述网络热点相关推荐数据包。The second selection module 120 is used to select multiple network data from the network database based on two linear functions to form the network hotspot related recommendation data package if the data is within a preset range.
在一个实施例中，所述第二计算模块90，包括：In one embodiment, the second calculation module 90 includes:
输入子模块，用于将所述波动指标值和多个所述网络热点输入至预设的函数获取模型中，得到对应的转换函数；其中，所述函数获取模型根据不同的网络热点和指标值作为输入，以及根据对应的转换函数作为输出训练而成；The input submodule is used to input the fluctuation index value and a plurality of the network hot spots into a preset function acquisition model to obtain the corresponding conversion function; wherein the function acquisition model is based on different network hot spots and index values. As input, and trained according to the corresponding transformation function as output;
映射子模块，用于根据所述转换函数对所述网络数据进行空间映射，得到每个网络数据映射后的目标网络数据；A mapping submodule, used to spatially map the network data according to the conversion function to obtain the target network data mapped by each network data;
计算子模块，用于基于所述目标网络数据计算计算每条线性函数与对应网络数据的欧式距离。The calculation submodule is used to calculate the Euclidean distance between each linear function and the corresponding network data based on the target network data.
在一个实施例中，所述第一计算模块50，包括：In one embodiment, the first calculation module 50 includes:
波动指标值计算子模块，用于根据公式计算各个所述维度数值集合的波动指标值，其中/>其中，Ei表示第i个维度数值集合的所述波动指标值，当pij＝0时，定义limpij→0pijlnpij＝0，pij表示第i个维度数值集合中的第j个热点评论对应的中间值，/>表示第i个维度数值集合中的第j个热点评论对应的标准值，n表示热点评论的个数，xij表示第i个维度数值集合中的第j个热点评论对应的维度数值，min(xij)和max(xij)分别表示第i个维度数值集合中最小值和最大值。Volatility indicator value calculation submodule, used to calculate according to the formula Calculate the volatility index value of each dimension value set, where/> Among them, Ei represents the fluctuation index value of the i-th dimension value set. When pij =0, define limpij→0 pij lnpij =0, and pij represents the j-th value set of the i-th dimension. The median value corresponding to hot comments,/> represents the standard value corresponding to the j-th hot comment in the i-th dimension value set, n represents the number of hot comments, xij represents the dimension value corresponding to the j-th hot comment in the i-th dimension value set, min( xij ) and max(xij ) respectively represent the minimum value and maximum value in the i-th dimension value set.
在一个实施例中，所述基于舆情热点的数据管理系统，还包括：In one embodiment, the data management system based on public opinion hot spots also includes:
调整模块，用于若不在预设的范围内，则调整所述线性函数中的权重向量，直至所述变换参数在所述预设的范围内，得到两个目标线性函数；an adjustment module, configured to adjust the weight vector in the linear function until the transformation parameter is within the preset range if it is not within the preset range, and obtain two target linear functions;
网络数据选取模块，用于基于两个所述目标线性函数从网络数据库中选取多个网络数据，以形成所述网络热点相关推荐数据包。A network data selection module is used to select multiple network data from the network database based on the two target linear functions to form the network hotspot related recommendation data package.
在一个实施例中，所述基于舆情热点的数据管理系统，还包括：In one embodiment, the data management system based on public opinion hot spots also includes:
时间信息获取模块，用于获取各个选取的网络数据的时间信息；The time information acquisition module is used to obtain the time information of each selected network data;
优先级顺序设置模块，用于基于所述时间信息为各个网络数据设置优先级顺序；A priority order setting module, configured to set a priority order for each network data based on the time information;
推送模块，用于基于所述优先级顺序向用户有序推送各个所述网络数据。A push module, configured to push each of the network data to users in an orderly manner based on the priority order.
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一非易失性计算机可读取存储介质中，该计算机程序在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的和实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可以包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM一多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage. In the media, when executed, the computer program may include the processes of the above method embodiments. Any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and/or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM) , memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、装置、物品或者方法不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、装置、物品或者方法所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、装置、物品或者方法中还存在另外的相同要素。It should be noted that, in this document, the terms "comprising", "comprising" or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, device, article or method that includes a series of elements not only includes those elements, It also includes other elements not expressly listed or inherent in the process, apparatus, article or method. Without further limitation, an element defined by the statement "comprises a..." does not exclude the presence of additional identical elements in a process, apparatus, article or method that includes that element.
本申请实施例可以基于人工智能技术对相关的数据进行获取和处理。其中，人工智能(Artificial Intelligence，AI)是利用数字计算机或者数字计算机控制的机器模拟、延伸和扩展人的智能，感知环境、获取知识并使用知识获得最佳结果的理论、方法、技术及应用系统。The embodiments of this application can obtain and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or digital computer-controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. .
人工智能基础技术一般包括如传感器、专用人工智能芯片、云计算、分布式存储、大数据处理技术、操作/交互系统、机电一体化等技术。人工智能软件技术主要包括计算机视觉技术、机器人技术、生物识别技术、语音处理技术、自然语言处理技术以及机器学习/深度学习等几大方向。Basic artificial intelligence technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation/interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, robotics technology, biometric technology, speech processing technology, natural language processing technology, and machine learning/deep learning.
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于本领域的技术人员来说，本发明可以有各种更改和变化。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的权利要求范围之内。The above descriptions are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of the claims of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310801706.7ACN116821502B (en) | 2023-06-30 | 2023-06-30 | Public opinion hotspot-based data management method and system |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310801706.7ACN116821502B (en) | 2023-06-30 | 2023-06-30 | Public opinion hotspot-based data management method and system |
| Publication Number | Publication Date |
|---|---|
| CN116821502Atrue CN116821502A (en) | 2023-09-29 |
| CN116821502B CN116821502B (en) | 2024-03-08 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310801706.7AActiveCN116821502B (en) | 2023-06-30 | 2023-06-30 | Public opinion hotspot-based data management method and system |
| Country | Link |
|---|---|
| CN (1) | CN116821502B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751458A (en)* | 2009-12-31 | 2010-06-23 | 暨南大学 | Network public sentiment monitoring system and method |
| CN104077377A (en)* | 2014-06-25 | 2014-10-01 | 红麦聚信(北京)软件技术有限公司 | Method and device for finding network public opinion hotspots based on network article attributes |
| CN104346425A (en)* | 2014-07-28 | 2015-02-11 | 中国科学院计算技术研究所 | Method and system of hierarchical internet public sentiment indication system |
| CN104504150A (en)* | 2015-01-09 | 2015-04-08 | 成都布林特信息技术有限公司 | News public opinion monitoring system |
| CN105718590A (en)* | 2016-01-27 | 2016-06-29 | 福州大学 | Multi-tenant oriented SaaS public opinion monitoring system and method |
| CN110188265A (en)* | 2019-04-26 | 2019-08-30 | 中国科学院计算技术研究所 | A network public opinion hotspot recommendation method and system integrating user portraits |
| CN111461553A (en)* | 2020-04-02 | 2020-07-28 | 上饶市中科院云计算中心大数据研究院 | System and method for monitoring and analyzing public sentiment in scenic spot |
| CN112380859A (en)* | 2020-11-12 | 2021-02-19 | 平安科技（深圳）有限公司 | Public opinion information recommendation method and device, electronic equipment and computer storage medium |
| CN113536805A (en)* | 2021-07-09 | 2021-10-22 | 北京奇艺世纪科技有限公司 | Public opinion analysis method, device, equipment and storage medium for hotspot events |
| CN113613081A (en)* | 2021-09-29 | 2021-11-05 | 深圳佳力拓科技有限公司 | Program recommendation method and device based on target program recommendation model |
| CN113779415A (en)* | 2021-10-22 | 2021-12-10 | 平安科技（深圳）有限公司 | Training method, device and equipment of news recommendation model and storage medium |
| CN114298157A (en)* | 2021-12-06 | 2022-04-08 | 重庆邮电大学 | Short text sentiment classification method, medium and system based on public opinion big data analysis |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751458A (en)* | 2009-12-31 | 2010-06-23 | 暨南大学 | Network public sentiment monitoring system and method |
| CN104077377A (en)* | 2014-06-25 | 2014-10-01 | 红麦聚信(北京)软件技术有限公司 | Method and device for finding network public opinion hotspots based on network article attributes |
| CN104346425A (en)* | 2014-07-28 | 2015-02-11 | 中国科学院计算技术研究所 | Method and system of hierarchical internet public sentiment indication system |
| CN104504150A (en)* | 2015-01-09 | 2015-04-08 | 成都布林特信息技术有限公司 | News public opinion monitoring system |
| CN105718590A (en)* | 2016-01-27 | 2016-06-29 | 福州大学 | Multi-tenant oriented SaaS public opinion monitoring system and method |
| CN110188265A (en)* | 2019-04-26 | 2019-08-30 | 中国科学院计算技术研究所 | A network public opinion hotspot recommendation method and system integrating user portraits |
| CN111461553A (en)* | 2020-04-02 | 2020-07-28 | 上饶市中科院云计算中心大数据研究院 | System and method for monitoring and analyzing public sentiment in scenic spot |
| CN112380859A (en)* | 2020-11-12 | 2021-02-19 | 平安科技（深圳）有限公司 | Public opinion information recommendation method and device, electronic equipment and computer storage medium |
| CN113536805A (en)* | 2021-07-09 | 2021-10-22 | 北京奇艺世纪科技有限公司 | Public opinion analysis method, device, equipment and storage medium for hotspot events |
| CN113613081A (en)* | 2021-09-29 | 2021-11-05 | 深圳佳力拓科技有限公司 | Program recommendation method and device based on target program recommendation model |
| CN113779415A (en)* | 2021-10-22 | 2021-12-10 | 平安科技（深圳）有限公司 | Training method, device and equipment of news recommendation model and storage medium |
| CN114298157A (en)* | 2021-12-06 | 2022-04-08 | 重庆邮电大学 | Short text sentiment classification method, medium and system based on public opinion big data analysis |
| Publication number | Publication date |
|---|---|
| CN116821502B (en) | 2024-03-08 |
| Publication | Publication Date | Title |
|---|---|---|
| US11514260B2 (en) | Information recommendation method, computer device, and storage medium | |
| US12411897B2 (en) | Recommendation model training method and related apparatus | |
| CN108829808B (en) | Page personalized sorting method and device and electronic equipment | |
| US11314988B2 (en) | Image aesthetic processing method and electronic device | |
| US9807473B2 (en) | Jointly modeling embedding and translation to bridge video and language | |
| RU2696230C2 (en) | Search based on combination of user relations data | |
| US10445379B2 (en) | Method of generating a training object for training a machine learning algorithm | |
| WO2021151336A1 (en) | Road image target detection method based on attentional mechanism and related device | |
| US11017019B1 (en) | Style classification for authentic content search | |
| CN111797320A (en) | Data processing method, device, equipment and storage medium | |
| US11288538B2 (en) | Object functionality predication methods, computer device, and storage medium | |
| JP2008539528A (en) | Scoring user compatibility in social networks | |
| CN116601626A (en) | Personal knowledge map construction method, device and related equipment | |
| WO2017151899A1 (en) | Determining key concepts in documents based on a universal concept graph | |
| EP2715574A1 (en) | Method and apparatus of providing suggested terms | |
| JP7237905B2 (en) | Method, apparatus and system for data mapping | |
| US11651255B2 (en) | Method and apparatus for object preference prediction, and computer readable medium | |
| CN110889747A (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation system, computer equipment and storage medium | |
| CN110147833A (en) | Facial image processing method, apparatus, system and readable storage medium storing program for executing | |
| WO2021139106A1 (en) | Grouping decision-making model generation method and apparatus, grouping processing method and apparatus, and device and medium | |
| CN112732898A (en) | Document abstract generation method and device, computer equipment and storage medium | |
| CN115130493A (en) | Face deformation recommendation method, device, equipment and medium based on image recognition | |
| WO2024099032A1 (en) | Image classification method and apparatus and computer device | |
| CN113366420B (en) | Image processing method, computer readable storage medium and computer device | |
| CN108875083B (en) | Social network-based person searching method and device, computer equipment and storage medium |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |